Generalizing semi-supervised and unsupervised learning for domain adaptation with very large scientific data

Lunga, Dalton D.; Page, David Lon; Hughes, David

Title: Generalizing semi-supervised and unsupervised learning for domain adaptation with very large scientific data

Full Record
Other Related Research

Authors:

^[1];

^[1]

ORNL

Publication Date:: Thu Mar 01 00:00:00 EST 2018

Research Org.:: Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)

Sponsoring Org.:: USDOE

OSTI Identifier:: 1474449

DOE Contract Number:: AC05-00OR22725

Resource Type:: Conference

Resource Relation:: Conference: DOE ASCR Scientific Machine Learning (SciML 2018) - Washington DC, District of Columbia, United States of America - 1/29/2018 3:00:00 PM-2/1/2018 3:00:00 PM

Country of Publication:: United States

Language:: English

Citation Formats


                    Lunga, Dalton D., Page, David Lon, and Hughes, David. Generalizing semi-supervised and unsupervised learning for domain adaptation with very large scientific data.  United States: N. p., 2018. 
        Web.

Copy to clipboard


                    Lunga, Dalton D., Page, David Lon, & Hughes, David. Generalizing semi-supervised and unsupervised learning for domain adaptation with very large scientific data.  United States.

Copy to clipboard


                    Lunga, Dalton D., Page, David Lon, and Hughes, David. 2018.  
        "Generalizing semi-supervised and unsupervised learning for domain adaptation with very large scientific data".  United States.  https://www.osti.gov/servlets/purl/1474449.

Copy to clipboard


                    
@article{osti_1474449,

  title        = {Generalizing semi-supervised and unsupervised learning for domain adaptation with very large scientific data},

  author       = {Lunga, Dalton D. and Page, David Lon and Hughes, David},

  abstractNote = {},

  doi          = {},

  url          = {https://www.osti.gov/biblio/1474449},
  journal      = {},
number       = ,

  volume       = ,

  place        = {United States},

  year         = {Thu Mar 01 00:00:00 EST 2018},

  month        = {Thu Mar 01 00:00:00 EST 2018}

}

Copy to clipboard

Conference:

View Conference (0.11 MB)

Other availability

Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share:

Export Metadata

Save to My Library

Similar records in OSTI.GOV collections:

Large Scale Unsupervised Domain Adaptation of Segmentation Networks with Adversarial Learning

Conference Deng, Xueqing; Yang, Lexie; Makkar, Nikhil; ...

Most current state-of-the-art methods for semantic segmentation on remote sensing imagery require large labeled data, which is scarcely available. Due to the distribution shifting phenomenon inherent in remote sensing imagery, the reuse of pre-trained models on new areas of interest rarely yield satisfactory results. In this paper, we approach this problem from an adversarial learning perspective toward unsupervised domain adaptation. The core concept is to infuse fully convolutional neural networks and adversarial networks for semantic segmentation assuming the structures in the scene and objects of interest are similar in two set of images. Models are trained on a source datasetmore »« less
https://doi.org/10.1109/IGARSS.2019.8900277

Full Text Available
Entropy and Boundary Based Adversarial Learning for Large Scale Unsupervised Domain Adaptation

Conference Makkar, Nikhil; Yang, Lexie

Supervised semantic segmentation methods provide state-of-the-art performance, but their performance is limited by the amount of quality labeled data they need for training. Scarcity of labeled data and non-transferablity of models, due to cross-domain discrepancy makes it a bigger challenge for remote sensing imagery analysis. In this work, we approach this problem through adversarial learning, driven by entropy and boundary of region-of-interest for unsupervised domain adaptation. This concept helps with better boundary prediction and encourages target domain entropy maps (probability/uncertainty maps) to be similar to source domains. In particular, we showed that deriving informative entropy through the adversarial learning ismore »« less
https://doi.org/10.1109/IGARSS39084.2020.9323863

Full Text Available
Semi-Supervised Domain Adaptation for Cross-Survey Galaxy Morphology Classification and Anomaly Detection

Conference Ćiprijanović, Aleksandra; Lewis, Ashia; Pedro, Kevin; ...

In the era of big astronomical surveys, our ability to leverage artificial intelligence algorithms simultaneously for multiple datasets will open new avenues for scientific discovery. Unfortunately, simply training a deep neural network on images from one data domain often leads to very poor performance on any other dataset. Here we develop a Universal Domain Adaptation method DeepAstroUDA, capable of performing semi-supervised domain alignment that can be applied to datasets with different types of class overlap. Extra classes can be present in any of the two datasets, and the method can even be used in the presence of unknown classes. Formore »« less
Full Text Available
Semi-Supervised Domain Adaptation for Cross-Survey Galaxy Morphology Classification and Anomaly Detection

Conference Ćiprijanović, Aleksandra; Lewis, Ashia; Pedro, Kevin; ...
https://doi.org/10.2172/1915406

Full Text Available
Multisource Data Classification Using A Hybrid Semi-supervised Learning Scheme

Conference Vatsavai, Raju; Bhaduri, Budhendra; Shekhar, Shashi; ...

In many practical situations thematic classes can not be discriminated by spectral measurements alone. Often one needs additional features such as population density, road density, wetlands, elevation, soil types, etc. which are discrete attributes. On the other hand remote sensing image features are continuous attributes. Finding a suitable statistical model and estimation of parameters is a challenging task in multisource (e.g., discrete and continuous attributes) data classification. In this paper we present a semi-supervised learning method by assuming that the samples were generated by a mixture model, where each component could be either a continuous or discrete distribution. Overall classificationmore »« less

Similar Records